Tangyu Jiang

Tangyu Jiang

Postdoc at TMLR

I am Tangyu Jiang, a Postdoctoral Researcher at TMLR Group of Hong Kong Baptist University (HKBU), advised by Prof. Bo Han. My research interests broadly lie in large language models and agentic systems, with a particular focus on LLM/agent efficiency. I received my Ph.D. degree from the School of Artificial Intelligence at Beijing Normal University. Prior to that, I obtained my Master’s degree from the School of Mathematical Sciences at Beijing Normal University and my Bachelor’s degree from the School of Mathematical Sciences at Dalian University of Technology.

Education and Experience

  • 2025.09-present, Postdoctoral Researcher, TMLR Group, Hong Kong Baptist University, advised by Prof. Bo Han.

  • 2021.09-2024.07, Ph.D. in School of Artificial Intelligence, Beijing Normal University.

  • 2018.09-2021.07, M.S. in School of Mathematical Sciences, Beijing Normal University.

  • 2014.09-2018.07, B.S. in School of Mathematical Sciences, Dalian University of Technology.

Selected Publications

  1. Accelerating Zero-Shot NAS With Feature Map-Based Proxy and Operation Scoring Function. T. Jiang, H. Wang, R. Bie, and C. Yuan. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.

  2. Comrope: Scalable and robust rotary position embedding parameterized by trainable commuting angle matrices. H. Yu, T. Jiang, S. Jia, S. Yan, S. Liu, H. Qian, G. Li, S. Dong, and C. Yuan. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025).

  3. Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking. Z. Su, X. Qiu, H. Xu, T. Jiang, J. Zhuang, C. Yuan, M. Li, S. He, and F. Yu. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. (NeurIPS 2025).

  4. Label noise correction for federated learning: a secure, efficient and reliable realization. H. Wang, T. Jiang, Y. Guo, F. Guo, R. Bie, and X. Jia. IEEE 40th International Conference on Data Engineering (ICDE 2024).

  5. Meco: zero-shot nas with one data and single forward pass via minimum eigenvalue of correlation. T. Jiang, H. Wang, and R. Bie. In Advances in Neural Information Processing Systems 36 (NeurIPS 2023), [Spotlight].

Awards

No notable awards yet — working hard toward earning some in the future. 🙂

Services

Conference Reviewer:

  • Neural Information Processing Systems (NeurIPS)
  • International Conference on Machine Learning (ICML)
  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • AAAI Conference on Artificial Intelligence (AAAI)

Journal Reviewer:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • Neural Networks (NN)